Re: [PATCH 5/5] IB/srp: Optimize completion queue polling

[Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org>]

On 07/03/14 18:46, Or Gerlitz wrote:
> On Thu, Jul 3, 2014 at 4:48 PM, Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org> wrote:
> [...]
>>
>> Limit the number of poll cycles per completion notification to preserve fairness
> 
> [...]
> 
> Any reason not to make use of the block layer NAPI like API for that
> (blk-iopoll http://lwn.net/Articles/346187/) ?

Hello Or,

As you maybe remember about four years ago I have been experimenting
with adding blk-iopoll support in the SRP initiator. What I learned at
that time is that the blk-iopoll framework defers work to softirq
context. This means that a context switch from interrupt to softirq
context has to occur before SRP completion processing can start. Recent
measurements on current hardware have shown that such a context switch
takes about 0.5 microseconds. Since I prefer to keep the latency of SRP
I/O as low as possible I haven't looked further into using blk-iopoll
for the SRP initiator driver.

Bart.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html